Preventing Oversmoothing in VAE via Generalized Variance Parameterization

CR-VAE：用于防止后验坍塌的变分自编码器对比正则化

CR-VAE: Contrastive Regularization on Variational Autoencoders for Preventing Posterior Collapse

针对VAE因目标函数局限导致的后验坍塌问题，提出CR-VAE方法，通过引入对比目标最大化相似输入间互信息，有效防止后验坍塌并在视觉数据集上优于现有方法。

Preventing Posterior Collapse with delta-VAEs

Due to the phenomenon of "posterior collapse," current latent variable generative models pose a challenging design choice that either weakens the capacity of the decoder or requires augmenting the objective so it does not only maximize the likelihood of the data. In this paper, we propose an alternative that utilizes the most powerful generative models as decoders, whilst optimising the variational lower bound all while ensuring that the latent variables preserve and encode useful information. Our proposed $δ$-VAEs achieve this by constraining the variational family for the posterior to have a…

Preventing Posterior Collapse with Levenshtein Variational Autoencoder

Variational autoencoders (VAEs) are a standard framework for inducing latent variable models that have been shown effective in learning text representations as well as in text generation. The key challenge with using VAEs is the {\it posterior collapse} problem: learning tends to converge to trivial solutions where the generators ignore latent variables. In our Levenstein VAE, we propose to replace the evidence lower bound (ELBO) with a new objective which is simple to optimize and prevents posterior collapse. Intuitively, it corresponds to generating a sequence from the autoencoder and encour…

使用几何变分自编码器建模巴雷特食管进展

Modeling Barrett's Esophagus Progression using Geometric Variational Autoencoders

针对巴雷特食管早期检测需求，研究几何变分自编码器捕捉其进展潜在表示的效果，验证两类几何VAE的性能提升，并提出兼具生成能力与自编码器优势的新型架构。

针对基于潜在扩散模型的图像编辑的灰盒攻击

A Gray-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapse

本文提出了一种基于后验崩溃现象的灰盒攻击方法，通过调整参数实现两种崩溃类型，有效防止未经授权的图像编辑，且对模型依赖低，计算效率高。

防止高斯过程潜变量模型中的模型坍塌

Preventing Model Collapse in Gaussian Process Latent Variable Models

针对高斯过程潜变量模型因核灵活性不足、投影噪声不当引发的模型坍塌问题，本文结合谱混合核与可微随机傅里叶特征核近似提出advisedRFLVM，在潜表征质量和缺失数据插补上优于多种主流模型。